© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 25860
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unconventional
    -0.16
     specialised
    -0.14
     specialized
    -0.13
     unusual
    -0.12
     specially
    -0.12
     indirect
    -0.11
     uncommon
    -0.11
    special
    -0.11
     special
    -0.11
     extreme
    -0.10
    POSITIVE LOGITS
     standard
    0.21
     heterosexual
    0.20
     conventional
    0.20
     mainstream
    0.19
     traditional
    0.17
     classic
    0.17
     terrestrial
    0.17
     orthodox
    0.17
     Standard
    0.17
    _standard
    0.16
    Activations Density 4.480%

    No Known Activations